# DIRESA, a distance-preserving nonlinear dimension reduction technique based on regularized autoencoders

arXiv: https://arxiv.org/abs/2404.18314 · HTML: https://mlsanity.com/paper/2404.18314/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 40 references that are in the map.
- First posted on arXiv 28 Apr 2024.

## Builds on (most cited first, 8 of 8)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Compressing multidimensional weather and climate data into neural networks](https://mlsanity.com/paper/2210.12538/) (2022)
- [A test case for application of convolutional neural networks to spatio-temporal climate data: Re-identifying clustered weather patterns](https://mlsanity.com/paper/1811.04817/) (2018)
- [AtmoDist: Self-supervised Representation Learning for Atmospheric Dynamics](https://mlsanity.com/paper/2202.01897/) (2022)
- [A PCA-like Autoencoder](https://mlsanity.com/paper/1904.01277/) (2019)
- [Machine Learning Techniques to Construct Patched Analog Ensembles for Data Assimilation](https://mlsanity.com/paper/2103.00318/) (2021)
- [MASS-UMAP: Fast and accurate analog ensemble search in weather radar archive](https://mlsanity.com/paper/1910.01211/) (2019)

## Built on by (most cited first, 1 of 1)

- [AI reconstruction of European weather from the Euro-Atlantic regimes](https://mlsanity.com/paper/2506.13758/) (2025)

## Abstract (arXiv)

In meteorology, finding similar weather patterns or analogs in historical datasets can be useful for data assimilation, forecasting, and postprocessing. In climate science, analogs in historical and climate projection data are used for attribution and impact studies. However, most of the time, those large weather and climate datasets are nearline. This means that they must be downloaded, which takes a lot of bandwidth and disk space, before the computationally expensive search can be executed. We propose a dimension reduction technique based on autoencoder (AE) neural networks to compress the datasets and perform the search in an interpretable, compressed latent space. A distance-regularized Siamese twin autoencoder (DIRESA) architecture is designed to preserve distance in latent space while capturing the nonlinearities in the datasets. Using conceptual climate models of different complexities, we show that the latent components thus obtained provide physical insight into the dominant modes of variability in the system. Compressing datasets with DIRESA reduces the online storage and keeps the latent components uncorrelated, while the distance (ordering) preservation and reconstruction fidelity robustly outperform Principal Component Analysis (PCA) and other dimension reduction techniques such as UMAP or variational autoencoders.